Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 664 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.4975. Min Act: -0.1700

Data Index: 2244198 (Open Web Text)

Max Activating Token Index: 927

Text #1

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.4453. Min Act: -0.1700

Data Index: 6741957 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2824. Min Act: -0.1700

Data Index: 2645343 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.3063. Min Act: -0.1700

Data Index: 5434453 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2827. Min Act: -0.1700

Data Index: 3429219 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2878. Min Act: -0.1700

Data Index: 7611028 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2089. Min Act: -0.1700

Data Index: 5533447 (Open Web Text)

Max Activating Token Index: 887

Text #7

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2297. Min Act: -0.1700

Data Index: 5991432 (Open Web Text)

Max Activating Token Index: 162

Text #8

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1644. Min Act: -0.1700

Data Index: 3099907 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1423. Min Act: -0.1700

Data Index: 1782563 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1389. Min Act: -0.1700

Data Index: 4399783 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1573. Min Act: -0.1700

Data Index: 8253611 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1573. Min Act: -0.1700

Data Index: 5454725 (Open Web Text)

Max Activating Token Index: 922

Text #13

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1510. Min Act: -0.1700

Data Index: 429231 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1549. Min Act: -0.1700

Data Index: 4523916 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1349. Min Act: -0.1700

Data Index: 4221265 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1079. Min Act: -0.1700

Data Index: 5477483 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1483. Min Act: -0.1700

Data Index: 2186142 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.0982. Min Act: -0.1700

Data Index: 201595 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1082. Min Act: -0.1700

Data Index: 6124045 (Open Web Text)

Max Activating Token Index: 435